{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WLTMAQLVM6GKFXG3J2CKRES6XO","short_pith_number":"pith:WLTMAQLV","schema_version":"1.0","canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","source":{"kind":"arxiv","id":"2605.27039","version":1},"attestation_state":"computed","paper":{"title":"Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Eun-Jung Holden, Han Yin, Hong Jia, Siyi Wang, Ting Dang, Vidhyasaharan Sethu, Yang Xiao","submitted_at":"2026-05-26T13:56:33Z","abstract_excerpt":"Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech) understanding remains poorly understood, and the underlying mechanisms of representation and retrieval are still unclear. This work introduces EnvMem, a controlled multi-turn benchmark designed to study this gap and identify the root causes of failures at the representation (i.e., latent embeddings) and retrieval levels (i.e., attention allocation). We furthe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.27039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-26T13:56:33Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"edc65622d9f3789f21065b7ceb869e093bbd3ac207123ad0da49efcaff24b3b5","abstract_canon_sha256":"880a70a9b5b6111233c7e448fe1877016f38ee18db94c2662d2895a7d4286417"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:25.347939Z","signature_b64":"X/FSX++O5JJ875Q/b7zdVNme4UEaEANI71vlaaUo/KzCuvhOl4TQ4arG89stJ5VfsML01MFNwVcDqp8Gs6KiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e6c04175678ca2dcdb4e84a8925ebbbbef276179363d75aa4fe8355ea93c50","last_reissued_at":"2026-05-27T01:06:25.347159Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:25.347159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Eun-Jung Holden, Han Yin, Hong Jia, Siyi Wang, Ting Dang, Vidhyasaharan Sethu, Yang Xiao","submitted_at":"2026-05-26T13:56:33Z","abstract_excerpt":"Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech) understanding remains poorly understood, and the underlying mechanisms of representation and retrieval are still unclear. This work introduces EnvMem, a controlled multi-turn benchmark designed to study this gap and identify the root causes of failures at the representation (i.e., latent embeddings) and retrieval levels (i.e., attention allocation). We furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27039","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.27039/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27039","created_at":"2026-05-27T01:06:25.347266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27039v1","created_at":"2026-05-27T01:06:25.347266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27039","created_at":"2026-05-27T01:06:25.347266+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLTMAQLVM6GK","created_at":"2026-05-27T01:06:25.347266+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLTMAQLVM6GKFXG3","created_at":"2026-05-27T01:06:25.347266+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLTMAQLV","created_at":"2026-05-27T01:06:25.347266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO","json":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO.json","graph_json":"https://pith.science/api/pith-number/WLTMAQLVM6GKFXG3J2CKRES6XO/graph.json","events_json":"https://pith.science/api/pith-number/WLTMAQLVM6GKFXG3J2CKRES6XO/events.json","paper":"https://pith.science/paper/WLTMAQLV"},"agent_actions":{"view_html":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO","download_json":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO.json","view_paper":"https://pith.science/paper/WLTMAQLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27039&json=true","fetch_graph":"https://pith.science/api/pith-number/WLTMAQLVM6GKFXG3J2CKRES6XO/graph.json","fetch_events":"https://pith.science/api/pith-number/WLTMAQLVM6GKFXG3J2CKRES6XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/action/storage_attestation","attest_author":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/action/author_attestation","sign_citation":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/action/citation_signature","submit_replication":"https://pith.science/pith/WLTMAQLVM6GKFXG3J2CKRES6XO/action/replication_record"}},"created_at":"2026-05-27T01:06:25.347266+00:00","updated_at":"2026-05-27T01:06:25.347266+00:00"}